Project Description

As Generative AI is everywhere around, we want to research its possibilities, how it can help SUSE, its employees and customers. The initial idea is to build solution based on Amazon Bedrock, to integrate our asset management tools and to be able to query the data and get the answers using human-like text.

Goal for this Hackweek

Populate all available data from SUSE Asset management tools (integrate with Jira Insight, Racktables, CloudAccountMetadata, Cloudquery,...) into the foundational model (e.g. Amazon Titan). Then make the foundational model able to answer simple queries like how many VMs are running in PRG2 or who are the owners of EC2 instances of t2 family.

This is only one of the ideas for GenAI we have. Most probably we will try to cover also another scenarios. If you are interested or you have any other idea how to utilize foundational models, let us know.

Resources

  • https://aws.amazon.com/bedrock/
  • https://github.com/aws-samples/amazon-bedrock-workshop
  • Specifically for this hackweek was created AWS Account ITPE Gen IA Dev (047178302800) accessible via Okta - whoever is interested, please contact me (or raise JiraSD ticket to be added to CLZ: ITPE Gen IA Dev) and use region us-west-2 (don't mind the typo, heh).
  • we have booked AWS engineer, expert on Bedrock on 2023-11-06 (1-5pm CET, meeting link) - anyone interested can join

Keywords

AI, GenAI, GenerativeAI, AWS, Amazon Bedrock, Amazon Titan, Asset Management

Looking for hackers with the skills:

ai genai generativeai aws amazontitan assetmanagement bedrock

This project is part of:

Hack Week 23

Activity

  • almost 2 years ago: vadim joined this project.
  • almost 2 years ago: ralwal joined this project.
  • almost 2 years ago: rjagu joined this project.
  • almost 2 years ago: rjagu left this project.
  • almost 2 years ago: rjagu joined this project.
  • almost 2 years ago: lthadeus liked this project.
  • almost 2 years ago: ralwal liked this project.
  • about 2 years ago: mpiala started this project.
  • about 2 years ago: mpiala added keyword "bedrock" to this project.
  • about 2 years ago: mpiala removed keyword amazonbedrock from this project.
  • about 2 years ago: mpiala added keyword "assetmanagement" to this project.
  • about 2 years ago: mpiala added keyword "ai" to this project.
  • about 2 years ago: mpiala added keyword "genai" to this project.
  • about 2 years ago: mpiala added keyword "generativeai" to this project.
  • about 2 years ago: mpiala added keyword "aws" to this project.
  • about 2 years ago: mpiala added keyword "amazonbedrock" to this project.
  • about 2 years ago: mpiala added keyword "amazontitan" to this project.
  • about 2 years ago: mpiala originated this project.

  • Comments

    • mpiala
      almost 2 years ago by mpiala | Reply

      slides from the AWS workshop: https://mysuse.sharepoint.com/:b:/s/suse-it-infra/EYUbSRf1y5NqAq9Owjh6cQB0ESOJnJRzx83P5d2EzTMA?e=j8miG1

    • mpiala
      almost 2 years ago by mpiala | Reply

      and recording of the workshop: Gen AI with AWS-20231106_130308-Meeting Recording.mp4

    • vadim
      almost 2 years ago by vadim | Reply

      @mpiala now that we all have some hands on experience with bedrock I suggest that you create a few workgroup sessions for tomorrow / Thursday and invite contributors. I'd split the work into three workstreams:

      1. Create infrastructure / pipelines that would deploy the project in a reproducible way
      2. Create a crawler that would parse the source data and populate a vector database (probably a lambda that can be triggered by cloudwatch)
      3. Create a backend that would query the vector DB, run inference and integrate with slack

      For vector DB we can use something off the shelf, like pinecone.io - later we can move it to Athena or something else.

    Similar Projects

    Flaky Tests AI Finder for Uyuni and MLM Test Suites by oscar-barrios

    Description

    Our current Grafana dashboards provide a great overview of test suite health, including a panel for "Top failed tests." However, identifying which of these failures are due to legitimate bugs versus intermittent "flaky tests" is a manual, time-consuming process. These flaky tests erode trust in our test suites and slow down development.

    This project aims to build a simple but powerful Python script that automates flaky test detection. The script will directly query our Prometheus instance for the historical data of each failed test, using the jenkins_build_test_case_failure_age metric. It will then format this data and send it to the Gemini API with a carefully crafted prompt, asking it to identify which tests show a flaky pattern.

    The final output will be a clean JSON list of the most probable flaky tests, which can then be used to populate a new "Top Flaky Tests" panel in our existing Grafana test suite dashboard.

    Goals

    By the end of Hack Week, we aim to have a single, working Python script that:

    1. Connects to Prometheus and executes a query to fetch detailed test failure history.
    2. Processes the raw data into a format suitable for the Gemini API.
    3. Successfully calls the Gemini API with the data and a clear prompt.
    4. Parses the AI's response to extract a simple list of flaky tests.
    5. Saves the list to a JSON file that can be displayed in Grafana.
    6. New panel in our Dashboard listing the Flaky tests

    Resources